using System;
using System.IO;
using System.Linq;
using System.Threading;
using xAiModels.Models;
using System.Threading.Tasks;
using xAiApi.Interfaces.Extractors;
namespace xAiApi.Providers.Extractors
{
public class XImageFileContentExtractor : IXImageFileContentExtractor
{
///
/// Supported MIME Types ...
///
private static readonly string[] SupportedMimeTypes =
[
"image/png",
"image/jpeg",
"image/jpg",
"image/gif",
"image/webp",
"image/bmp"
];
///
/// آیا OCR فعال است (برای مدلهای غیر Vision) ...
///
private readonly bool _enableOcrFallback;
public XImageFileContentExtractor() : this(enableOcrFallback: true)
{ }
public XImageFileContentExtractor(bool enableOcrFallback = true)
{
_enableOcrFallback = enableOcrFallback;
}
///
/// Check if this extractor supports the specified MIME type ...
///
public bool CanExtract(string mimeType)
{
//
return SupportedMimeTypes.Contains(
mimeType?.ToLowerInvariant() ?? string.Empty
);
}
///
/// Extract text content from file stream ...
///
public async Task ExtractAsync(
Stream fileStream,
string mimeType,
CancellationToken cancellationToken = default
)
{
//
var result = await ExtractRichAsync(
fileStream,
"image",
mimeType,
cancellationToken
);
//
return result.Text;
}
///
/// Extract content from stream as Rich Result ...
///
///
///
///
///
///
public async Task ExtractRichAsync(
Stream fileStream,
string fileName,
string mimeType,
CancellationToken cancellationToken = default
)
{
//
var result = new XFileExtractionResult
{
FileName = fileName,
MimeType = mimeType
};
//
using var memoryStream = new MemoryStream();
await fileStream.CopyToAsync(memoryStream, cancellationToken);
var imageBytes = memoryStream.ToArray();
//
result.Images.Add(new XExtractedImage
{
Bytes = imageBytes,
MimeType = mimeType,
Description = $"Attached image: {fileName}"
});
// OCR Fallback برای مدلهای متنی
if (_enableOcrFallback)
{
//
try
{
//
var ocrText = await PerformOcrAsync(imageBytes, cancellationToken);
if (!string.IsNullOrWhiteSpace(ocrText))
{
result.Text = ocrText;
}
}
catch
{
// OCR failed, but image is still available for Vision
}
}
//
return result;
}
///
/// Do OCR on Image for Text Extraction ...
///
private async Task PerformOcrAsync(
byte[] imageBytes,
CancellationToken cancellationToken
)
{
//
// TODO: Complete this ...
return await Task.FromResult(string.Empty);
}
}
}